@adonis-agora/agent 0.82.0 → 0.84.0

package/CHANGELOG.md

@@ -1,5 +1,28 @@
 # @adonis-agora/agent
 
+## 0.84.0
+
+### Minor Changes
+
+- [#440](https://github.com/DavideCarvalho/adonis-agora-agent/pull/440) [`c113c76`](https://github.com/DavideCarvalho/adonis-agora-agent/commit/c113c76a890b076caab8bc143c7d2a10d570b7be) Thanks [@DavideCarvalho](https://github.com/DavideCarvalho)! - A run's time to first token, failure code and model are stored, and the governance dashboard and the Telescope tab chart them:
+  
+  - **Stored on the run.** `agent_run` gains nullable `ttft_ms`, `error_code` and `model_id`, added by `createAgentTables`' schema repair (run at boot; with `autoCreateTables: false`, re-run the `create_agent_tables` migration). `RecordRunEndInput` takes `ttftMs`, `errorCode` and `modelId`. A completed run records its time to first token and last model; a failed one records the same stable code its stream `error` frame carries (`quota_exceeded`, `model_no_output`, `run_failed`…), next to the `error` text as before. A run found dead, or failed by OpenCode, is `run_failed`. `RunSummaryRow` carries the three as optional fields.
+  - **Tool timing.** A tool call's `execution_ms` is now filled, measured inside its `tool:<id>` checkpoint: how long the tool ran, not how long a replay took to read it back. A replayed call writes none.
+  - **Read-model.** `RunReliability` gains optional `latency: { ttft, duration }` (`{ samples, p50Ms, p95Ms }`, nearest-rank, over completed turns a person started; a delegation's child run is left out) and `failuresByCode` (`{ code, count }[]`, most frequent first; a failure from before codes is `unknown`). `PerToolStatRow` gains optional `p50ExecutionMs` / `p95ExecutionMs`. `summarizeLatency` / `summarizeRunMetrics` are exported; `GenuiLatency` is now an alias of the shared `Latency`.
+  - **Dashboard.** Reliability shows time to first token and turn duration (p50 / p95) and a failures-by-code donut and table; Tools shows p50 / p95 per tool.
+  - **Telescope.** A new "Run latency" section: TTFT and turn-duration distributions (p50 / p95 / p99) from `run.finished`, and failures by code from `run.failed` (`agent.latency`, `agent.failuresByCode`). Active runs now subtract `run.failed` and `run.cancelled` too, and the tool-call counters skip a call re-published on replay.
+
+## 0.83.0
+
+### Minor Changes
+
+- [#438](https://github.com/DavideCarvalho/adonis-agora-agent/pull/438) [`decd556`](https://github.com/DavideCarvalho/adonis-agora-agent/commit/decd556d9ed1e51be39efcd763e513fdbbe4c879) Thanks [@DavideCarvalho](https://github.com/DavideCarvalho)! - More of a run on its diagnostics, so an observer can chart failures, cost and slow tools without reading the store:
+  
+  - **`agora:agent:run.failed`** when the loop throws, with the same stable `code` the stream's `error` frame carries (`quota_exceeded`, `model_no_output`, `run_failed`…) and `durationMs`. Never the error itself. A durable control-flow signal (suspend on an approval or a question) is not an ending and publishes nothing.
+  - **`agora:agent:run.cancelled`** when the run's abort signal fired.
+  - **`run.finished`** also carries `costUsd` (when any step's cost is known), `modelId` (the last model call's), and who the run is: `agentName`, `actorId`, `tenantRef`, and `parentRunId` on a delegation's child run. `run.failed` and `run.cancelled` carry the same.
+  - **`tool-call`** carries `toolCallId`, and `durationMs` when this process ran the tool. A call whose checkpoint the durable runtime read back from the journal is published again with `replayed: true` and no duration, so counting observers can skip it.
+
 ## 0.82.0
 
 ### Minor Changes